Performance monitoring of a multi-product semi-batch process

Abstract Traditionally principal components analysis (PCA) has been viewed as a single-population method. In particular in multivariate statistical process control, PCA has been used to monitor single product production. An extension to principal components analysis is presented which enables the simultaneous monitoring of a number of product grades or recipes. The method is based upon the existence of a common eigenvector subspace for the sample variance–covariance matrices of the individual products. The pooled sample variance–covariance matrix of the individual products is then used to estimate the principal component loadings of the multi-group model. The methodology is applied to a semi-discrete industrial batch process manufacturing a number of recipes. The industrial application illustrates that the detection and diagnostic capabilities of the multi-group model are comparable to those achieved by developing a separate statistical representation for the individual products.